**Polynomial Regression** is a form of linear regression in which the relationship between the independent variable x and dependent variable y is modeled as an nth degree polynomial. Polynomial regression fits a nonlinear relationship between the value of x and the corresponding conditional mean of y, denoted E(y|x). Basically it adds the quadratic or polynomial terms to the regression. Generally, this kind of regression is used for one resultant variable and one predictor.

#### Need of Polynomial Regression

- Unlike linear data set, if one tries to apply linear model on non-linear data set without any modification, then there will be a very unsatisfactory and drastic result .
- This may lead to increase in loss function, decrease in accuracy and high error rate.
- Unlike linear model, polynomial model covers more data points.

#### Applications of Polynomial Regression

Generally, polynomial regression is used in the following scenarios :

- Rate of growth of tissues.
- Progression of the epidemics related to disease.
- Distribution phenomenon of the isotopes of carbon in lake sediments.

#### Explanation of Polynomial Regression in R Programming

Polynomial Regression is also known as Polynomial Linear Regression since it depends on the linearly arranged coefficients rather than the variables. In R, if one wants to implement polynomial regression then he must install the following packages:

**tidyverse**package for better visualization and manipulation.**caret**package for a smoother and easier machine learning workflow.

After proper installation of the packages, one needs to set the data properly. For that, first one needs to split the data into two sets(train set and test set). Then one can visualize the data into various plots. In R, in order to fit a polynomial regression, first one needs to generate pseudo random numbers using the ** set.seed(n)** function.

The polynomial regression adds polynomial or quadratic terms to the regression equation as follow:

medv = b0 + b1 * lstat + b2 * lstat^{2}

where

mdev:is the median house value

lstat:is the predictor variable

In R, to create a predictor x^{2} one should use the function

, as follow: **I()**

. This raise x to the power 2. The polynomial regression can be computed in R as follow:**I(x ^{2})**

lm(medv ~ lstat + I(lstat^2), data = train.data)

For this following example let’s take the Boston data set of MASS package.

**Example:**

`# R program to illustrate ` `# Polynomial regression ` ` ` `# Imporing required library ` `library` `(tidyverse) ` `library` `(caret) ` `theme_set` `(` `theme_classic` `()) ` ` ` `# Load the data ` `data` `(` `"Boston"` `, package = ` `"MASS"` `) ` `# Split the data into training and test set ` `set.seed` `(123) ` `training.samples <- Boston$medv %>% ` ` ` `createDataPartition` `(p = 0.8, list = ` `FALSE` `) ` `train.data <- Boston[training.samples, ] ` `test.data <- Boston[-training.samples, ] ` ` ` `# Build the model ` `model <- ` `lm` `(medv ~ ` `poly` `(lstat, 5, raw = ` `TRUE` `), ` ` ` `data = train.data) ` `# Make predictions ` `predictions <- model %>% ` `predict` `(test.data) ` `# Model performance ` `modelPerfomance = ` `data.frame` `( ` ` ` `RMSE = ` `RMSE` `(predictions, test.data$medv), ` ` ` `R2 = ` `R2` `(predictions, test.data$medv) ` ` ` `) ` ` ` `print` `(` `lm` `(medv ~ lstat + ` `I` `(lstat^2), data = train.data)) ` `print` `(modelPerfomance) ` |

*chevron_right*

*filter_none*

**Output:**

Call: lm(formula = medv ~ lstat + I(lstat^2), data = train.data) Coefficients: (Intercept) lstat I(lstat^2) 42.5736 -2.2673 0.0412 RMSE R2 1 5.270374 0.6829474

**Graph plotting of Polynomial Regression**

In R, if one wants to plot a graph for the output generated on implementing Polynomial Regression he can use the ** ggplot()** function.

**Example:**

`# R program to illustrate ` `# Graph plotting in ` `# Polynomial regression ` ` ` `# Importing required library ` `library` `(tidyverse) ` `library` `(caret) ` `theme_set` `(` `theme_classic` `()) ` ` ` `# Load the data ` `data` `(` `"Boston"` `, package = ` `"MASS"` `) ` `# Split the data into training and test set ` `set.seed` `(123) ` `training.samples <- Boston$medv %>% ` ` ` `createDataPartition` `(p = 0.8, list = ` `FALSE` `) ` `train.data <- Boston[training.samples, ] ` `test.data <- Boston[-training.samples, ] ` ` ` `# Build the model ` `model <- ` `lm` `(medv ~ ` `poly` `(lstat, 5, raw = ` `TRUE` `), data = train.data) ` `# Make predictions ` `predictions <- model %>% ` `predict` `(test.data) ` `# Model performance ` `data.frame` `(RMSE = ` `RMSE` `(predictions, test.data$medv), ` ` ` `R2 = ` `R2` `(predictions, test.data$medv)) ` ` ` `ggplot` `(train.data, ` `aes` `(lstat, medv) ) + ` `geom_point` `() + ` `stat_smooth` `(method = lm, formula = y ~ ` `poly` `(x, 5, raw = ` `TRUE` `)) ` |

*chevron_right*

*filter_none*

**Output:**

## Recommended Posts:

- Find roots or zeros of a Polynomial in R Programming - polyroot() Function
- Poisson Regression in R Programming
- Logistic Regression in R Programming
- Regression Analysis in R Programming
- Perform Linear Regression Analysis in R Programming - lm() Function
- Random Forest Approach for Regression in R Programming
- Lasso Regression in R Programming
- Regression and its Types in R Programming
- Regression using k-Nearest Neighbors in R Programming
- Decision Tree for Regression in R Programming
- R-squared Regression Analysis in R Programming
- Ridge Regression in R Programming
- Elastic Net Regression in R Programming
- Quantile Regression in R Programming
- Regression with Categorical Variables in R Programming
- Types of Regression Techniques
- Getting the Modulus of the Determinant of a Matrix in R Programming - determinant() Function
- Set or View the Graphics Palette in R Programming - palette() Function
- tidyr Package in R Programming
- Get Exclusive Elements between Two Objects in R Programming - setdiff() Function

If you like GeeksforGeeks and would like to contribute, you can also write an article using contribute.geeksforgeeks.org or mail your article to contribute@geeksforgeeks.org. See your article appearing on the GeeksforGeeks main page and help other Geeks.

Please Improve this article if you find anything incorrect by clicking on the "Improve Article" button below.